sudban3089 / ID-Preserving-Facial-Aging

Identity-Preserving Aging of Face Images via Latent Diffusion Models [IJCB 2023]
MIT License
24 stars 5 forks source link

__init__() got an unexpected keyword argument 'biometric_weight' #5

Open baiyun442 opened 5 days ago

baiyun442 commented 5 days ago

when I train the Cosine loss,there has a TypeError:

` python main.py --base configs/stable-diffusion/v1-finetune_cosineloss.yaml -t --actual_resume stable-diffusion/v1-5-pruned.ckpt -n test1 --gpus 0, --data_root IJCB2023_TrainExamples/SubID_0029_NumImages_19/ --reg_data_root CelebA_regularization_NEW/ --class_word person --no-test

Global seed set to 23 Running on GPUs 0, Loading model from stable-diffusion/v1-5-pruned.ckpt LatentDiffusion: Running in eps-prediction mode DiffusionWrapper has 859.52 M params. Traceback (most recent call last): File "main.py", line 638, in model = load_model_from_config(config, opt.actual_resume) File "main.py", line 29, in load_model_from_config model = instantiate_from_config(config.model) File "/home/aiyun/ID-Preserving-Facial-Aging-main/ID-Preserving-Facial-Aging-main/ldm/util.py", line 86, in instantiate_from_config return get_obj_from_str(config["target"])(config.get("params", dict()), kwargs) File "/home/aiyun/ID-Preserving-Facial-Aging-main/ID-Preserving-Facial-Aging-main/ldm/models/diffusion/ddpm_cosineembedding.py", line 483, in init self.instantiate_first_stage(first_stage_config) File "/home/aiyun/ID-Preserving-Facial-Aging-main/ID-Preserving-Facial-Aging-main/ldm/models/diffusion/ddpm_cosineembedding.py", line 543, in instantiate_first_stage model = instantiate_from_config(config) File "/home/aiyun/ID-Preserving-Facial-Aging-main/ID-Preserving-Facial-Aging-main/ldm/util.py", line 86, in instantiate_from_config return get_obj_from_str(config["target"])(config.get("params", dict()), kwargs) TypeError: init() got an unexpected keyword argument 'biometric_weight'

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "main.py", line 851, in if trainer.global_rank == 0: NameError: name 'trainer' is not defined ` why does it happen? what should I do? Any suggestions?

sudban3089 commented 5 days ago

I have commented out biometric_weight in v1-finetune_cosineloss.yaml (Line 57) as that was not defined or needed in ddpm_cosineembedding.py. Hope this solves the issue.

baiyun442 commented 13 hours ago

It works! Thank you!